GNN代码调试过程中遇到的问题（求解贴）

Question

GNN代码调试过程中遇到的问题

最近在学习GNN的代码，但是在调试的过程中发现有两个模块之间有冲突，GNN源码地址如下：

https://github.com/graphdeeplearning/benchmarking-gnns

用代码块功能插入代码，请勿粘贴截图

其中的好几个案例，用到了dgl的库，但是我用anaconda python3.7运行后发现，要求pytorch的版本必须大于1.9

import dgl  # 调用这个库时，提示pytorch必须大于1.9

然后，在就该pytorch的版本为1.12（当然目前似乎看官网已经更新到1.13）
然后再点击运行，发现又有报错。

运行结果及报错内容

Traceback (most recent call last):
  File "D:\Anaconda\lib\site-packages\torch_sparse\__init__.py", line 15, in <module>
    library, [osp.dirname(__file__)]).origin)
  File "D:\Anaconda\lib\site-packages\torch\_ops.py", line 255, in load_library
    ctypes.CDLL(path)
  File "D:\Anaconda\lib\ctypes\__init__.py", line 356, in __init__
    self._handle = _dlopen(self._name, mode)
OSError: [WinError 127] 找不到指定的程序。

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "E:/研究生作业2021-2024/研二（上）/2022写过的代码（pytorch）/1105第二篇小论文代码/benchmarking-gnns-master/main_COLLAB_edge_classification.py", line 45, in <module>
    from data.data import LoadData # import dataset
  File "E:\研究生作业2021-2024\研二（上）\2022写过的代码（pytorch）\1105第二篇小论文代码\benchmarking-gnns-master\data\data.py", line 9, in <module>
    from data.COLLAB import COLLABDataset
  File "E:\研究生作业2021-2024\研二（上）\2022写过的代码（pytorch）\1105第二篇小论文代码\benchmarking-gnns-master\data\COLLAB.py", line 6, in <module>
    from ogb.linkproppred import DglLinkPropPredDataset, Evaluator
  File "D:\Anaconda\lib\site-packages\ogb\linkproppred\__init__.py", line 5, in <module>
    from .dataset_pyg import PygLinkPropPredDataset
  File "D:\Anaconda\lib\site-packages\ogb\linkproppred\dataset_pyg.py", line 6, in <module>
    from torch_geometric.data import InMemoryDataset
  File "D:\Anaconda\lib\site-packages\torch_geometric\__init__.py", line 4, in <module>
    import torch_geometric.data
  File "D:\Anaconda\lib\site-packages\torch_geometric\data\__init__.py", line 1, in <module>
    from .data import Data
  File "D:\Anaconda\lib\site-packages\torch_geometric\data\data.py", line 20, in <module>
    from torch_sparse import SparseTensor
  File "D:\Anaconda\lib\site-packages\torch_sparse\__init__.py", line 21, in <module>
    f'Expected PyTorch version {t_major}.{t_minor} but found '
RuntimeError: Expected PyTorch version 1.4 but found version 1.12.

我的解答思路和尝试过的方法

我目前暂时未找到解决方法，求各路神仙解答。

Answer 1

RuntimeError: Expected PyTorch version 1.4 but found version 1.12
RuntimeError:应为PyTorch版本1.4，但找到版本1.12

你的报错和这篇帖子很相似，分享给你作为参考，看是否能帮助到你：https://www.zhihu.com/question/489835978/answer/2207443973